timeline_compute_all

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does a fair job: it discloses the performance trait (slow on large designs), the side-effect class (a full recompute), and the failure-reporting shape via {"ok": true, "errors": []}. It does not say whether the rebuild can partially fail, whether the document must be saved first, or whether it mutates the timeline itself.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action, then the return, then the cost/usage caveat, ending with a compact example. Every sentence adds distinct information with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by asserting the return matches timeline_health plus an inline example with ok/errors fields. The reliance on a sibling's report shape is a minor gap only for an agent that has never called timeline_health.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so the baseline is 4. The example call timeline_compute_all() reinforces the empty-argument invocation and leaves nothing ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Recompute the whole design (Design.computeAll)") and names the exact artifact returned (timeline_health report). This clearly separates it from the read-only sibling timeline_health and from execute_python, which would otherwise be a plausible way to trigger a rebuild.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit conditions for use: when the model looks stale, or after edits made via execute_python, plus a cost warning ("Slow on big designs") that implies when to avoid it. It stops short of naming timeline_health or other siblings as a cheaper alternative for a read-only check.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.